Loomis Painter: Reconstructing the Painting Process

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pobitzer, Markus, Liu, Chang, Zhuang, Chenyi, Long, Teng, Ren, Bin, Sebe, Nicu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908678795296768
author Pobitzer, Markus
Liu, Chang
Zhuang, Chenyi
Long, Teng
Ren, Bin
Sebe, Nicu
author_facet Pobitzer, Markus
Liu, Chang
Zhuang, Chenyi
Long, Teng
Ren, Bin
Sebe, Nicu
contents Step-by-step painting tutorials are vital for learning artistic techniques, but existing video resources (e.g., YouTube) lack interactivity and personalization. While recent generative models have advanced artistic image synthesis, they struggle to generalize across media and often show temporal or structural inconsistencies, hindering faithful reproduction of human creative workflows. To address this, we propose a unified framework for multi-media painting process generation with a semantics-driven style control mechanism that embeds multiple media into a diffusion models conditional space and uses cross-medium style augmentation. This enables consistent texture evolution and process transfer across styles. A reverse-painting training strategy further ensures smooth, human-aligned generation. We also build a large-scale dataset of real painting processes and evaluate cross-media consistency, temporal coherence, and final-image fidelity, achieving strong results on LPIPS, DINO, and CLIP metrics. Finally, our Perceptual Distance Profile (PDP) curve quantitatively models the creative sequence, i.e., composition, color blocking, and detail refinement, mirroring human artistic progression.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17344
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Loomis Painter: Reconstructing the Painting Process
Pobitzer, Markus
Liu, Chang
Zhuang, Chenyi
Long, Teng
Ren, Bin
Sebe, Nicu
Computer Vision and Pattern Recognition
Step-by-step painting tutorials are vital for learning artistic techniques, but existing video resources (e.g., YouTube) lack interactivity and personalization. While recent generative models have advanced artistic image synthesis, they struggle to generalize across media and often show temporal or structural inconsistencies, hindering faithful reproduction of human creative workflows. To address this, we propose a unified framework for multi-media painting process generation with a semantics-driven style control mechanism that embeds multiple media into a diffusion models conditional space and uses cross-medium style augmentation. This enables consistent texture evolution and process transfer across styles. A reverse-painting training strategy further ensures smooth, human-aligned generation. We also build a large-scale dataset of real painting processes and evaluate cross-media consistency, temporal coherence, and final-image fidelity, achieving strong results on LPIPS, DINO, and CLIP metrics. Finally, our Perceptual Distance Profile (PDP) curve quantitatively models the creative sequence, i.e., composition, color blocking, and detail refinement, mirroring human artistic progression.
title Loomis Painter: Reconstructing the Painting Process
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.17344